Supervised Device Charting with CSI Measurements from Commercial 5G NR User Equipments
Abstract
Radio frequency fingerprint identification (RFFI) is a promising approach to distinguish physical wireless devices using hardware-induced signal imperfections. Conventional RFFI methods only provide discrete device labels and no human-interpretable representation of the relations among received signals. We propose supervised device charting, which maps location-insensitive channel-state information (CSI) fingerprints to a low-dimensional chart that visualizes cluster compactness, overlap, and outliers. We evaluate the method with real-world 5G New Radio (5G NR) measurements from six commercial smartphones and introduce the neighbor label error rate (NLER) to quantify class-separation accuracy. Our results demonstrate that two- and three-dimensional device charts provide an interpretable visualization of the learned RFFI representation. For three-dimensional device charts, the NLER is 0.22% for same-day measurements and 7.38% for measurements from the next day. The device charts reveal a cross-day distribution shift and map the held-out device close to the known device of the same model. Increasing the device chart dimensions further improves cluster separation at the expense of interpretability.
Related
- ForkSCOPE: Charting the Agentic Garden of Forking Paths
- Semiparametrically efficient semi-supervised statistical inference
- Application of spectroscopic and multispectral imaging technologies on the assessment of ready-to-eat pineapple quality: A performance evaluation study of machine learning models generated from two commercial data analytics tools
- Semi-supervised learning on singular data sets
- Corrections to ``The Method of Gaps: Exact Expressions for the Generalization Error of Supervised Learning Algorithms
BibTeX
@misc{vasylyev2026supervised,
title = {{Supervised Device Charting with CSI Measurements from Commercial 5G NR User Equipments}},
author = {Mischa Vasylyev and Frederik Zumegen and Reinhard Wiesmayr and Christoph Studer},
howpublished = {arXiv},
year = {2026},
month = sep,
doi = {10.48550/arxiv.2609.24213},
eprint = {2609.24213},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2609.24213},
}
RIS
TY - UNPB
TI - Supervised Device Charting with CSI Measurements from Commercial 5G NR User Equipments
AU - Mischa Vasylyev
AU - Frederik Zumegen
AU - Reinhard Wiesmayr
AU - Christoph Studer
PY - 2026
DA - 2026/09/21
PB - arXiv
DO - 10.48550/arxiv.2609.24213
UR - https://arxiv.org/abs/2609.24213
AB - Radio frequency fingerprint identification (RFFI) is a promising approach to distinguish physical wireless devices using hardware-induced signal imperfections. Conventional RFFI methods only provide discrete device labels and no human-interpretable representation of the relations among received signals. We propose supervised device charting, which maps location-insensitive channel-state information (CSI) fingerprints to a low-dimensional chart that visualizes cluster compactness, overlap, and outliers. We evaluate the method with real-world 5G New Radio (5G NR) measurements from six commercial smartphones and introduce the neighbor label error rate (NLER) to quantify class-separation accuracy. Our results demonstrate that two- and three-dimensional device charts provide an interpretable visualization of the learned RFFI representation. For three-dimensional device charts, the NLER is 0.22% for same-day measurements and 7.38% for measurements from the next day. The device charts reveal a cross-day distribution shift and map the held-out device close to the known device of the same model. Increasing the device chart dimensions further improves cluster separation at the expense of interpretability.
ER -